Bayesian Inference Using Synthetic Likelihood: Asymptotics and Adjustments
From MaRDI portal
Abstract: Implementing Bayesian inference is often computationally challenging in applications involving complex models, and sometimes calculating the likelihood itself is difficult. Synthetic likelihood is one approach for carrying out inference when the likelihood is intractable, but it is straightforward to simulate from the model. The method constructs an approximate likelihood by taking a vector summary statistic as being multivariate normal, with the unknown mean and covariance matrix estimated by simulation for any given parameter value. Our article makes three contributions. The first shows that if the summary statistic satisfies a central limit theorem, then the synthetic likelihood posterior is asymptotically normal and yields credible sets with the correct level of frequentist coverage. This result is similar to that obtained by approximate Bayesian computation. The second contribution compares the computational efficiency of Bayesian synthetic likelihood and approximate Bayesian computation using the acceptance probability for rejection and importance sampling algorithms with a "good" proposal distribution. We show that Bayesian synthetic likelihood is computationally more efficient than approximate Bayesian computation, and behaves similarly to regression-adjusted approximate Bayesian computation. Based on the asymptotic results, the third contribution proposes using adjusted inference methods when a possibly misspecified form is assumed for the covariance matrix of the synthetic likelihood, such as diagonal or a factor model, to speed up the computation. The methodology is illustrated with some simulated and real examples.
Cites work
- A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
- A General Framework for Updating Belief Distributions
- Accelerating Bayesian Synthetic Likelihood With the Graphical Lasso
- An MCMC approach to classical estimation.
- An extended empirical saddlepoint approximation for intractable likelihoods
- Asymptotic properties of approximate Bayesian computation
- Bayesian Synthetic Likelihood
- Bayesian indirect inference using a parametric auxiliary model
- Bayesian optimization for likelihood-free inference of simulator-based statistical models
- Bootstrap methods for dependent data: a review
- Convergence of regression-adjusted approximate Bayesian computation
- Efficient Bayesian Synthetic Likelihood With Whitening Transformations
- Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator
- Handbook of approximate Bayesian computation
- High-dimensional probability. An introduction with applications in data science
- Likelihood-free inference in high dimensions with synthetic likelihood
- Model Misspecification in Approximate Bayesian Computation: Consequences and Diagnostics
- On some properties of Markov chain Monte Carlo simulation methods based on the particle filter
- On the asymptotic efficiency of approximate Bayesian computation estimators
- On the efficiency of pseudo-marginal random walk Metropolis algorithms
- Penalized Normal Likelihood and Ridge Regularization of Correlation and Covariance Matrices
- Risk of Bayesian inference in misspecified models, and the sandwich covariance matrix
- Robust Approximate Bayesian Inference With Synthetic Likelihood
- Robust Bayesian synthetic likelihood via a semi-parametric approach
- The ABC of simulation estimation with auxiliary statistics
- The asymptotic distribution of serial covariances
- The correlated pseudomarginal method
- The pseudo-marginal approach for efficient Monte Carlo computations
- Variational Bayes with synthetic likelihood
Cited in
(7)- Using Early Rejection Markov Chain Monte Carlo and Gaussian Processes to Accelerate ABC Methods
- Synthetic Likelihood in Misspecified Models
- Transformations in semi-parametric Bayesian synthetic likelihood
- Box confidence depth: simulation-based inference with hyper-rectangles
- Bayesian Synthetic Likelihood
- Generalized Bayesian likelihood-free inference
- Robust Approximate Bayesian Inference With Synthetic Likelihood
This page was built for publication: Bayesian Inference Using Synthetic Likelihood: Asymptotics and Adjustments
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6185577)
